Posts

Showing posts from 2026

Connect Snowflake cloud from Pega Infinity using JDBC driver

Image
With simple steps, I was able to connect to Snowflake cloud from Pega Infinity community edition using JDBC driver option. We can also use the API service call from Pega to connect Snowflake but I am interested in this option to check the integration. Brief idea on Snowflake: Snowflake is a cloud-based data platform used to store, process, analyze, and share large volumes of data. It runs on cloud infrastructure such as AWS, Microsoft Azure, and Google Cloud. Think of Snowflake as a centralized data warehouse where an organization can bring data from many applications and analyze it using SQL. Snowflake separates storage, compute, and cloud services. Its virtual warehouses provide the compute resources that execute queries. Concept Simple explanation Database  Container for related data Schema  Organizes tables and views within a database Table  Stores structured data in rows and columns Virtual Warehouse  Compute engine that runs queries Role  Defines what...

Connect Pega Infinity with Aiven Kafka Cloud instance

Image
Here are the 5 simple steps to follow to connect Pega Infinity V26.x to Aiven Kafka cloud instance: Step 1 : Signup in  https://console.aiven.io/ and is free for 30 days. Sample snapshot used at my end. Step 2 : Login into Pega Community Edition running on V26.x and create a Kafka rule instance from Records -> SysAdmin   Step 3 : Create a Truststore and call it from the above Kafka rule instance Step 4 : Create a Data Set (Records -> Data Model) like below and call the above Kafka rule instance and add a topic to create in Aiven cloud instance   Step 5 : Create a simple activity and push the message to the Kafka topic to store and check the cloud instance to see the pushed message.

GitHub to Vercel ==> a Free live AI-powered website

Image
  Small projects like this are a great way to experiment with GenAI, APIs, cloud deployment, and secure application design together. 🔗 Live website: https://indian-veg-finder.vercel.app/ If you're learning AI application development, try taking one of your existing GitHub projects and turning it into a live application. 🚀 The live site itself describes the application as using Google Places for restaurant data and Gemini for the AI recommendation, so those points are directly aligned with what you have deployed. I recently built a small project called Thali Finder 🍛 to find Indian vegetarian restaurants based on a ZIP code, city, or address. Link for this Github project: https://github.com/RKPisupati/indian-veg-finder What started as a Python program running locally is now available as a live website: 👉 https://indian-veg-finder.vercel.app/ Here is the link where you can find the simple steps to bring your Github repository into Vercel: https://www.facebook.com/share/v/1EZ...

Simple understanding of Pega Knowledge Buddy functionality

Image
Pega Knowledge Buddy (KB) converts documents into searchable semantic chunks, stores their embeddings in a vector database, retrieves the most relevant chunks for a user's question, and gives those chunks to the LLM through RAG to generate a grounded answer. Step1: Ingestion — Build the Knowledge Base Document → Chunks → Embeddings → Vector Storage Source content Pega Knowledge articles PDFs/documents SharePoint content, etc. Chunking Knowledge Buddy breaks large content into smaller pieces called chunks . For example, the default SIZE approach uses 1,000 characters with 200-character overlap. Pega also supports TITLE and NONE chunking methods. Semantic/Embedding processing Each chunk is sent through the Pega GenAI Gateway . An embedding is generated — a numerical representation of the meaning of that chunk. Additional attributes/metadata can also be associated with the chunk, improving semantic retrieval. Vector storage The embeddings and associated chunk information are store...

Build Pega Applications with GitHub Copilot CLI, Pega Infinity AI Plugin & MCP — Branch-Based Agentic Authoring

Image
To work on this experiment, we need the Github Copilot CLI, Pega Infinity Instance, and Pega Infinity AI Plugins ( https://github.com/pegasystems/infinity-ai-plugins ) . In my case, I have used the Pega Infinity V26.1 Community Edition and here is the Github repository to upload it in the Github Copilot plugin marketplace. For this entire exercise to work well, we need Java 17 or above.  Windows Command Prompt (Agent-Driven Terminal): Represents the Github Copilot CLI. It shows the active terminal execution where commands like pega-setup, list-skills, list-available-applications etc. MCP (Model Context Protocol) Orchestrator: Acts as the bridge and mediator between the AI terminal environment (GitHub Copilot) and the Pega platform. It translates natural language directives and agent commands into structured operations and API calls to manage application configurations. Here the name of the MCP server is pega--infinity-authoring Workflow Directives: Represents...